Related
I'm trying to utilize make_pipeline() from scikit-learn along with GridSearchCV(). The Pipeline is simple and only includes two steps, a StandardScaler() and an MLPRegressor(). The GridSearchCV()is also pretty simple with the slight wrinkle that I'm using TimeSeriesSplit() for cross-validation.
The error I'm getting is as follows:
ValueError: Invalid parameter MLPRegressor for estimator Pipeline(steps=[('standardscaler', StandardScaler()),('mlpregressor', MLPRegressor())]). Check the list of available parameters with estimator.get_params().keys().
Can someone help me understand how I can rectify this problem so I can use the make_pipeline() framework with both GridSearchCV() and MLPRegressor() .
from sklearn.neural_network import MLPRegressor
...: from sklearn.preprocessing import StandardScaler
...: from sklearn.model_selection import TimeSeriesSplit, GridSearchCV
...: from sklearn.pipeline import make_pipeline
...: import numpy as np
In [2]: tscv = TimeSeriesSplit(n_splits = 5)
In [3]: pipe = make_pipeline(StandardScaler(), MLPRegressor())
In [4]: param_grid = {'MLPRegressor__hidden_layer_sizes': [(16,16,), (64,64,), (
...: 128,128,)], 'MLPRegressor__activation': ['identity', 'logistic', 'tanh',
...: 'relu'],'MLPRegressor__solver': ['adam','sgd']}
In [5]: grid = GridSearchCV(pipe, param_grid = param_grid, cv = tscv)
In [6]: features = np.random.random([1000,10])
In [7]: target = np.random.normal(0,10,1000)
In [8]: grid.fit(features, target)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-8-7233f9f2005e> in <module>
----> 1 grid.fit(features, target)
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
61 extra_args = len(args) - len(all_args)
62 if extra_args <= 0:
---> 63 return f(*args, **kwargs)
64
65 # extra_args > 0
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
839 return results
840
--> 841 self._run_search(evaluate_candidates)
842
843 # multimetric is determined here because in the case of a callable
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/sklearn/model_selection/_search.py in _run_search(self, evaluate_candidates)
1294 def _run_search(self, evaluate_candidates):
1295 """Search all candidates in param_grid"""
-> 1296 evaluate_candidates(ParameterGrid(self.param_grid))
1297
1298
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/sklearn/model_selection/_search.py in evaluate_candidates(candidate_params, cv, more_results)
793 n_splits, n_candidates, n_candidates * n_splits))
794
--> 795 out = parallel(delayed(_fit_and_score)(clone(base_estimator),
796 X, y,
797 train=train, test=test,
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/joblib/parallel.py in __call__(self, iterable)
1039 # remaining jobs.
1040 self._iterating = False
-> 1041 if self.dispatch_one_batch(iterator):
1042 self._iterating = self._original_iterator is not None
1043
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
857 return False
858 else:
--> 859 self._dispatch(tasks)
860 return True
861
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/joblib/parallel.py in _dispatch(self, batch)
775 with self._lock:
776 job_idx = len(self._jobs)
--> 777 job = self._backend.apply_async(batch, callback=cb)
778 # A job can complete so quickly than its callback is
779 # called before we get here, causing self._jobs to
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/joblib/_parallel_backends.py in apply_async(self, func, callback)
206 def apply_async(self, func, callback=None):
207 """Schedule a func to be run"""
--> 208 result = ImmediateResult(func)
209 if callback:
210 callback(result)
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/joblib/_parallel_backends.py in __init__(self, batch)
570 # Don't delay the application, to avoid keeping the input
571 # arguments in memory
--> 572 self.results = batch()
573
574 def get(self):
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/joblib/parallel.py in __call__(self)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/joblib/parallel.py in <listcomp>(.0)
260 # change the default number of processes to -1
261 with parallel_backend(self._backend, n_jobs=self._n_jobs):
--> 262 return [func(*args, **kwargs)
263 for func, args, kwargs in self.items]
264
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/sklearn/utils/fixes.py in __call__(self, *args, **kwargs)
220 def __call__(self, *args, **kwargs):
221 with config_context(**self.config):
--> 222 return self.function(*args, **kwargs)
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, split_progress, candidate_progress, error_score)
584 cloned_parameters[k] = clone(v, safe=False)
585
--> 586 estimator = estimator.set_params(**cloned_parameters)
587
588 start_time = time.time()
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/sklearn/pipeline.py in set_params(self, **kwargs)
148 self
149 """
--> 150 self._set_params('steps', **kwargs)
151 return self
152
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/sklearn/utils/metaestimators.py in _set_params(self, attr, **params)
52 self._replace_estimator(attr, name, params.pop(name))
53 # 3. Step parameters and other initialisation arguments
---> 54 super().set_params(**params)
55 return self
56
~/opt/miniconda3/envs/practice/lib/python3.9/site-packages/sklearn/base.py in set_params(self, **params)
228 key, delim, sub_key = key.partition('__')
229 if key not in valid_params:
--> 230 raise ValueError('Invalid parameter %s for estimator %s. '
231 'Check the list of available parameters '
232 'with `estimator.get_params().keys()`.' %
ValueError: Invalid parameter MLPRegressor for estimator Pipeline(steps=[('standardscaler', StandardScaler()),
('mlpregressor', MLPRegressor())]). Check the list of available parameters with `estimator.get_params().keys()`.
Solution
Yes. Make the pipeline first. Then treat the pipeline as your model and pass it to GridSearchCV.
Your problem is in the following line (you had it mislabeled):
Replace MLPRegressor__ with mlpregressor__.
The Fix:
The pipeline named_step for MLPRegressor estimator was mislabeled as MLPRegressor__ in the param_grid.
Changing it to mlpregressor__ fixed the problem.
You may run and check it in this colab notebook.
# INCORRECT
param_grid = {
'MLPRegressor__hidden_layer_sizes': [(16, 16,), (64, 64,), (128, 128,)],
'MLPRegressor__activation': ['identity', 'logistic', 'tanh', 'relu'],
'MLPRegressor__solver': ['adam', 'sgd'],
}
# CORRECTED
param_grid = {
'mlpregressor__hidden_layer_sizes': [(16, 16,), (64, 64,), (128, 128,)],
'mlpregressor__activation': ['identity', 'logistic', 'tanh', 'relu'],
'mlpregressor__solver': ['adam', 'sgd'],
}
Note
The key to understand what was wrong here, was to observe the last two lines of the error stack.
ValueError: Invalid parameter MLPRegressor for estimator Pipeline(steps=[('standardscaler', StandardScaler()),
('mlpregressor', MLPRegressor())]). Check the list of available parameters with `estimator.get_params().keys()`.
I am using Python 3.7 in a Jupyter Notebook. I am creating classification models based on Jason Brownlee's ebook Machine Learning Mastery with Python. The code is essentially cut and pasted from the ebook into the Jupyter Notebook. The models work fine when I split the data but when I use k-fold cross validation it generates a Future warning message I'll cut and paste the code and message below. I entered error_score =np.nan and it didn't fix the problem but I don't know where the code should be entered. I would appreciate any advice but keep in mind that I am a novice. Thanks
# Logistic Regression Classification
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
df = pd.read_csv('Diabetes_Classification.csv')
array = df.values
X = array[:,0:8]
Y = array[:,8]
kfold = KFold(n_splits=10, random_state=7)
model = LogisticRegression(solver='liblinear')
error_score = np.nan
results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())
# Logistic Regression Classification
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
df = pd.read_csv('Diabetes_Classification.csv')
array = df.values
X = array[:,0:8]
Y = array[:,8]
kfold = KFold(n_splits=10, random_state=7)
model = LogisticRegression(solver='liblinear')
error_score = np.nan
results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())
/Users/roberthoyt/opt/anaconda3/lib/python3.7/site-
packages/sklearn/model_selection/_validation.py:530: FutureWarning: From version 0.22, errors during
fit will result in a cross validation score of NaN by default. Use error_score='raise' if you want
an exception raised or error_score=np.nan to adopt the behavior from version 0.22.
FutureWarning)
ValueError Traceback (most recent call last)
<ipython-input-105-010e5612fd63> in <module>
11 model = LogisticRegression(solver='liblinear')
12 error_score = np.nan
---> 13 results = cross_val_score(model, X, Y, cv=kfold)
14 print(results.mean())
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in
cross_val_score(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch,
error_score)
389 fit_params=fit_params,
390 pre_dispatch=pre_dispatch,
--> 391 error_score=error_score)
392 return cv_results['test_score']
393
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in
cross_validate(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch,
return_train_score, return_estimator, error_score)
230 return_times=True, return_estimator=return_estimator,
231 error_score=error_score)
--> 232 for train, test in cv.split(X, y, groups))
233
234 zipped_scores = list(zip(*scores))
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in __call__(self, iterable)
919 # remaining jobs.
920 self._iterating = False
--> 921 if self.dispatch_one_batch(iterator):
922 self._iterating = self._original_iterator is not None
923
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in dispatch_one_batch(self,
iterator)
757 return False
758 else:
--> 759 self._dispatch(tasks)
760 return True
761
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in _dispatch(self, batch)
714 with self._lock:
715 job_idx = len(self._jobs)
--> 716 job = self._backend.apply_async(batch, callback=cb)
717 # A job can complete so quickly than its callback is
718 # called before we get here, causing self._jobs to
~/opt/anaconda3/lib/python3.7/site-packages/joblib/_parallel_backends.py in apply_async(self,
func,
callback)
180 def apply_async(self, func, callback=None):
181 """Schedule a func to be run"""
--> 182 result = ImmediateResult(func)
183 if callback:
184 callback(result)
~/opt/anaconda3/lib/python3.7/site-packages/joblib/_parallel_backends.py in __init__(self,
batch)
547 # Don't delay the application, to avoid keeping the input
548 # arguments in memory
--> 549 self.results = batch()
550
551 def get(self):
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in __call__(self)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py in <listcomp>(.0)
223 with parallel_backend(self._backend, n_jobs=self._n_jobs):
224 return [func(*args, **kwargs)
--> 225 for func, args, kwargs in self.items]
226
227 def __len__(self):
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/model_selection/_validation.py in _
fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params,
return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator,
error_score)
514 estimator.fit(X_train, **fit_params)
515 else:
--> 516 estimator.fit(X_train, y_train, **fit_params)
517
518 except Exception as e:
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/linear_model/logistic.py in fit(self, X, y,
sample_weight)
1531 X, y = check_X_y(X, y, accept_sparse='csr', dtype=_dtype, order="C",
1532 accept_large_sparse=solver != 'liblinear')
-> 1533 check_classification_targets(y)
1534 self.classes_ = np.unique(y)
1535 n_samples, n_features = X.shape
~/opt/anaconda3/lib/python3.7/site-packages/sklearn/utils/multiclass.py in
check_classification_targets(y)
167 if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
168 'multilabel-indicator', 'multilabel-sequences']:
--> 169 raise ValueError("Unknown label type: %r" % y_type)
170
171
ValueError: Unknown label type: 'continuous'
The problem is that your targets are continuous and you're doing a classification task. Make sure The column you're using a target is categorical. You may have to convert it to integer. All of this is reported in the traceback:
check_classification_targets(y)
167 if y_type not in ['binary', 'multiclass', 'multiclass-multioutput',
168 'multilabel-indicator', 'multilabel-sequences']:
--> 169 raise ValueError("Unknown label type: %r" % y_type)
Your target is not in the accepted targets. your target is continuous:
ValueError: Unknown label type: 'continuous'
Check if your target is an integer with df.dtypes and change it to integer if it isn't.
Y = array[:,8].astype(int)
That is assuming that you haven't made the mistake of making a classification task on continuous values. You can also check if all values represent 0s and 1s:
np.unique(array[:, 8])
I'm trying to use TransformedTargetRegressor in a model pipeline and run a GridSearchCV on top of it.
Here is a minimal working example:
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor
from sklearn.pipeline import Pipeline
from sklearn.model_selection import GridSearchCV
from sklearn.compose import TransformedTargetRegressor
X,y = make_regression()
model_pipe = Pipeline([
('model', TransformedTargetRegressor(RandomForestRegressor()))
])
params={'model__n_estimators': [1, 10, 50]}
model = GridSearchCV(model_pipe, param_grid= params)
model.fit(X,y)
This model results in the following error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-48-828bdf0e7ede> in <module>
17 model = GridSearchCV(model_pipe, param_grid= params)
18
---> 19 model.fit(X,y)
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
686 return results
687
--> 688 self._run_search(evaluate_candidates)
689
690 # For multi-metric evaluation, store the best_index_, best_params_ and
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/sklearn/model_selection/_search.py in _run_search(self, evaluate_candidates)
1147 def _run_search(self, evaluate_candidates):
1148 """Search all candidates in param_grid"""
-> 1149 evaluate_candidates(ParameterGrid(self.param_grid))
1150
1151
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/sklearn/model_selection/_search.py in evaluate_candidates(candidate_params)
665 for parameters, (train, test)
666 in product(candidate_params,
--> 667 cv.split(X, y, groups)))
668
669 if len(out) < 1:
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/joblib/parallel.py in __call__(self, iterable)
1001 # remaining jobs.
1002 self._iterating = False
-> 1003 if self.dispatch_one_batch(iterator):
1004 self._iterating = self._original_iterator is not None
1005
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
832 return False
833 else:
--> 834 self._dispatch(tasks)
835 return True
836
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/joblib/parallel.py in _dispatch(self, batch)
751 with self._lock:
752 job_idx = len(self._jobs)
--> 753 job = self._backend.apply_async(batch, callback=cb)
754 # A job can complete so quickly than its callback is
755 # called before we get here, causing self._jobs to
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/joblib/_parallel_backends.py in apply_async(self, func, callback)
199 def apply_async(self, func, callback=None):
200 """Schedule a func to be run"""
--> 201 result = ImmediateResult(func)
202 if callback:
203 callback(result)
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/joblib/_parallel_backends.py in __init__(self, batch)
580 # Don't delay the application, to avoid keeping the input
581 # arguments in memory
--> 582 self.results = batch()
583
584 def get(self):
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/joblib/parallel.py in __call__(self)
254 with parallel_backend(self._backend, n_jobs=self._n_jobs):
255 return [func(*args, **kwargs)
--> 256 for func, args, kwargs in self.items]
257
258 def __len__(self):
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/joblib/parallel.py in <listcomp>(.0)
254 with parallel_backend(self._backend, n_jobs=self._n_jobs):
255 return [func(*args, **kwargs)
--> 256 for func, args, kwargs in self.items]
257
258 def __len__(self):
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, error_score)
501 train_scores = {}
502 if parameters is not None:
--> 503 estimator.set_params(**parameters)
504
505 start_time = time.time()
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/sklearn/pipeline.py in set_params(self, **kwargs)
162 self
163 """
--> 164 self._set_params('steps', **kwargs)
165 return self
166
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/sklearn/utils/metaestimators.py in _set_params(self, attr, **params)
48 self._replace_estimator(attr, name, params.pop(name))
49 # 3. Step parameters and other initialisation arguments
---> 50 super().set_params(**params)
51 return self
52
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/sklearn/base.py in set_params(self, **params)
231
232 for key, sub_params in nested_params.items():
--> 233 valid_params[key].set_params(**sub_params)
234
235 return self
~/miniconda3/envs/gymbo/lib/python3.6/site-packages/sklearn/base.py in set_params(self, **params)
222 'Check the list of available parameters '
223 'with `estimator.get_params().keys()`.' %
--> 224 (key, self))
225
226 if delim:
ValueError: Invalid parameter n_estimators for estimator TransformedTargetRegressor(check_inverse=True, func=None, inverse_func=None,
regressor=RandomForestRegressor(bootstrap=True,
criterion='mse',
max_depth=None,
max_features='auto',
max_leaf_nodes=None,
min_impurity_decrease=0.0,
min_impurity_split=None,
min_samples_leaf=1,
min_samples_split=2,
min_weight_fraction_leaf=0.0,
n_estimators='warn',
n_jobs=None,
oob_score=False,
random_state=None,
verbose=0,
warm_start=False),
transformer=None). Check the list of available parameters with `estimator.get_params().keys()`.
This model runs when I remove TransformedTargetRegressor from the pipeline and just pass the random forest. Why is this? How can I use TransformedTargetRegressor in a pipeline as I have shown above?
The RandomForestRegressor is stored as regressor param in TransformedTargetRegressor.
Hence, the right way to define the params for GridSearchCV is
params={'model__regressor__n_estimators': [1, 10, 50]}
Seems like people are having issues with zeros in y. Consider the following using log1p and expm1. See another worked example here
X,y = make_regression()
model_pipe = Pipeline([
('model', TransformedTargetRegressor(regressor=RandomForestRegressor(),
func=np.log1p,
inverse_func=np.expm1))
])
params={'model__regressor__n_estimators': [1, 10, 50]}
model = GridSearchCV(model_pipe, param_grid= params)
model.fit(X,y)
I've found out the answer. The TransformedTargetregressor needs to be applied to the grid search estimator as so
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor
from sklearn.pipeline import Pipeline
from sklearn.model_selection import GridSearchCV
from sklearn.compose import TransformedTargetRegressor
X,y = make_regression()
model_pipe = Pipeline([
('model', RandomForestRegressor())
])
params={'model__n_estimators': [1, 10, 50]}
model = TransformedTargetRegressor(GridSearchCV(model_pipe, param_grid= params), func=np.log, inverse_func=np.exp)
model.fit(X,y)
Python sci-kit learn KNN Grid Search Cross Validation error
I am trying to recreated KNN model for prediction of car destination.
https://github.com/carlosbkm/car-destination-prediction
The code is not working at Grid search cross validation here:
https://github.com/carlosbkm/car-destination-prediction/blob/master/k-nearest-model.ipynb
At first geodash was not working so I switched it to geodash2 and there was no problem.
When I try to fit the model I get.
TypeError: unsupported operand type(s) for /: 'str' and 'int'
When I try to fit X and y for Grid Search Cross Validation I get an error.
The problem is coming from
def cv_optimize(clf, parameters, X, y, n_jobs=1, n_folds=5, score_func=None):
if score_func:
gs = GridSearchCV(clf, param_grid=parameters, cv=n_folds, n_jobs=n_jobs, scoring=score_func)
else:
gs = GridSearchCV(clf, param_grid=parameters, n_jobs=n_jobs, cv=n_folds)
gs.fit(X, y)
print ("BEST", gs.best_params_, gs.best_score_, gs.cv_results_)
best = gs.best_estimator_
return best
I can not fit the model to X and y:
gs.fit(X, y)
I tried to make X and y into floats but nothing changed
When I execute this:
# Create a k-Nearest Neighbors Regression estimator
knn_estimator = KNeighborsRegressor()
#knn_parameters = {"n_neighbors": [1,2,5,10,20,50,100]}
knn_parameters = {"n_neighbors": [1,2,5]}
knn_best = cv_optimize(knn_estimator, knn_parameters, X_train, y_train, score_func='neg_mean_squared_error')
I get:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-124-34b56429c6b5> in <module>()
4 #knn_parameters = {"n_neighbors": [1,2,5,10,20,50,100]}
5 knn_parameters = {"n_neighbors": [1,2,5]}
----> 6 knn_best = cv_optimize(knn_estimator, knn_parameters, X_train, y_train, score_func='neg_mean_squared_error')
<ipython-input-116-1a00f84f1047> in cv_optimize(clf, parameters, X, y, n_jobs, n_folds, score_func)
6 else:
7 gs = GridSearchCV(clf, param_grid=parameters, n_jobs=n_jobs, cv=n_folds)
----> 8 gs.fit(X, y)
9 print ("BEST", gs.best_params_, gs.best_score_, gs.cv_results_)
10 best = gs.best_estimator_
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups)
943 train/test set.
944 """
--> 945 return self._fit(X, y, groups, ParameterGrid(self.param_grid))
946
947
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/model_selection/_search.py in _fit(self, X, y, groups, parameter_iterable)
562 return_times=True, return_parameters=True,
563 error_score=self.error_score)
--> 564 for parameters in parameter_iterable
565 for train, test in cv_iter)
566
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self, iterable)
756 # was dispatched. In particular this covers the edge
757 # case of Parallel used with an exhausted iterator.
--> 758 while self.dispatch_one_batch(iterator):
759 self._iterating = True
760 else:
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in dispatch_one_batch(self, iterator)
606 return False
607 else:
--> 608 self._dispatch(tasks)
609 return True
610
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in _dispatch(self, batch)
569 dispatch_timestamp = time.time()
570 cb = BatchCompletionCallBack(dispatch_timestamp, len(batch), self)
--> 571 job = self._backend.apply_async(batch, callback=cb)
572 self._jobs.append(job)
573
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in apply_async(self, func, callback)
107 def apply_async(self, func, callback=None):
108 """Schedule a func to be run"""
--> 109 result = ImmediateResult(func)
110 if callback:
111 callback(result)
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py in __init__(self, batch)
324 # Don't delay the application, to avoid keeping the input
325 # arguments in memory
--> 326 self.results = batch()
327
328 def get(self):
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in __call__(self)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py in <listcomp>(.0)
129
130 def __call__(self):
--> 131 return [func(*args, **kwargs) for func, args, kwargs in self.items]
132
133 def __len__(self):
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, error_score)
258 else:
259 fit_time = time.time() - start_time
--> 260 test_score = _score(estimator, X_test, y_test, scorer)
261 score_time = time.time() - start_time - fit_time
262 if return_train_score:
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/model_selection/_validation.py in _score(estimator, X_test, y_test, scorer)
286 score = scorer(estimator, X_test)
287 else:
--> 288 score = scorer(estimator, X_test, y_test)
289 if hasattr(score, 'item'):
290 try:
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/metrics/scorer.py in __call__(self, estimator, X, y_true, sample_weight)
89 super(_PredictScorer, self).__call__(estimator, X, y_true,
90 sample_weight=sample_weight)
---> 91 y_pred = estimator.predict(X)
92 if sample_weight is not None:
93 return self._sign * self._score_func(y_true, y_pred,
~/anaconda3/envs/datascience/lib/python3.6/site-packages/sklearn/neighbors/regression.py in predict(self, X)
151
152 if weights is None:
--> 153 y_pred = np.mean(_y[neigh_ind], axis=1)
154 else:
155 y_pred = np.empty((X.shape[0], _y.shape[1]), dtype=np.float64)
~/anaconda3/envs/datascience/lib/python3.6/site-packages/numpy/core/fromnumeric.py in mean(a, axis, dtype, out, keepdims)
2907
2908 return _methods._mean(a, axis=axis, dtype=dtype,
-> 2909 out=out, **kwargs)
2910
2911
~/anaconda3/envs/datascience/lib/python3.6/site-packages/numpy/core/_methods.py in _mean(a, axis, dtype, out, keepdims)
71 if isinstance(ret, mu.ndarray):
72 ret = um.true_divide(
---> 73 ret, rcount, out=ret, casting='unsafe', subok=False)
74 if is_float16_result and out is None:
75 ret = arr.dtype.type(ret)
TypeError: unsupported operand type(s) for /: 'str' and 'int'
Want to use Gridsearch to find best parameters and use f1 as the scoring metric.
If i remove the scoring function, all works well and i get no errors.
Here is my code:
from sklearn import grid_search
parameters = {'n_neighbors':(1,3,5,10,15),'weights':('uniform','distance'),'algorithm':('ball_tree','kd_tree','brute'),'leaf_size':(5,10,20,30,50)}
reg = grid_search.GridSearchCV(estimator=neigh,param_grid=parameters,scoring="f1")
train_classifier(reg, X_train, y_train)
train_f1_score = predict_labels(reg, X_train, y_train)
print reg.best_params_
print "F1 score for training set: {}".format(train_f1_score)
print "F1 score for test set: {}".format(predict_labels(reg, X_test, y_test))
When i execute i get pages upon pages as errors, and i cannot make heads or tails of it :(
ValueError Traceback (most recent call last)
<ipython-input-17-3083ff8a20ea> in <module>()
3 parameters = {'n_neighbors':(1,3,5,10,15),'weights':('uniform','distance'),'algorithm':('ball_tree','kd_tree','brute'),'leaf_size':(5,10,20,30,50)}
4 reg = grid_search.GridSearchCV(estimator=neigh,param_grid=parameters,scoring="f1")
----> 5 train_classifier(reg, X_train, y_train)
6 train_f1_score = predict_labels(reg, X_train, y_train)
7 print reg.best_params_
<ipython-input-9-b56ce25fd90b> in train_classifier(clf, X_train, y_train)
5 print "Training {}...".format(clf.__class__.__name__)
6 start = time.time()
----> 7 clf.fit(X_train, y_train)
8 end = time.time()
9 print "Done!\nTraining time (secs): {:.3f}".format(end - start)
//anaconda/lib/python2.7/site-packages/sklearn/grid_search.pyc in fit(self, X, y)
802
803 """
--> 804 return self._fit(X, y, ParameterGrid(self.param_grid))
805
806
//anaconda/lib/python2.7/site-packages/sklearn/grid_search.pyc in _fit(self, X, y, parameter_iterable)
551 self.fit_params, return_parameters=True,
552 error_score=self.error_score)
--> 553 for parameters in parameter_iterable
554 for train, test in cv)
555
//anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self, iterable)
802 self._iterating = True
803
--> 804 while self.dispatch_one_batch(iterator):
805 pass
806
//anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in dispatch_one_batch(self, iterator)
660 return False
661 else:
--> 662 self._dispatch(tasks)
663 return True
664
//anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in _dispatch(self, batch)
568
569 if self._pool is None:
--> 570 job = ImmediateComputeBatch(batch)
571 self._jobs.append(job)
572 self.n_dispatched_batches += 1
//anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __init__(self, batch)
181 # Don't delay the application, to avoid keeping the input
182 # arguments in memory
--> 183 self.results = batch()
184
185 def get(self):
//anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in __call__(self)
70
71 def __call__(self):
---> 72 return [func(*args, **kwargs) for func, args, kwargs in self.items]
73
74 def __len__(self):
//anaconda/lib/python2.7/site-packages/sklearn/cross_validation.pyc in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, error_score)
1548
1549 else:
-> 1550 test_score = _score(estimator, X_test, y_test, scorer)
1551 if return_train_score:
1552 train_score = _score(estimator, X_train, y_train, scorer)
//anaconda/lib/python2.7/site-packages/sklearn/cross_validation.pyc in _score(estimator, X_test, y_test, scorer)
1604 score = scorer(estimator, X_test)
1605 else:
-> 1606 score = scorer(estimator, X_test, y_test)
1607 if not isinstance(score, numbers.Number):
1608 raise ValueError("scoring must return a number, got %s (%s) instead."
//anaconda/lib/python2.7/site-packages/sklearn/metrics/scorer.pyc in __call__(self, estimator, X, y_true, sample_weight)
88 else:
89 return self._sign * self._score_func(y_true, y_pred,
---> 90 **self._kwargs)
91
92
//anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.pyc in f1_score(y_true, y_pred, labels, pos_label, average, sample_weight)
637 return fbeta_score(y_true, y_pred, 1, labels=labels,
638 pos_label=pos_label, average=average,
--> 639 sample_weight=sample_weight)
640
641
//anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.pyc in fbeta_score(y_true, y_pred, beta, labels, pos_label, average, sample_weight)
754 average=average,
755 warn_for=('f-score',),
--> 756 sample_weight=sample_weight)
757 return f
758
//anaconda/lib/python2.7/site-packages/sklearn/metrics/classification.pyc in precision_recall_fscore_support(y_true, y_pred, beta, labels, pos_label, average, warn_for, sample_weight)
982 else:
983 raise ValueError("pos_label=%r is not a valid label: %r" %
--> 984 (pos_label, present_labels))
985 labels = [pos_label]
986 if labels is None:
ValueError: pos_label=1 is not a valid label: array(['no', 'yes'],
dtype='|S3')
Seems that you have label array with values 'no' and 'yes', you should convert them to binary 1-0 numerical representation, because your error states that scoring function cannot understand where 0's and 1's are in your label array.
Other possible way to solve it without modifying your label array:
from sklearn.metrics import f1_score
from sklearn.metrics import make_scorer
f1_scorer = make_scorer(f1_score, pos_label="yes")
reg = grid_search.GridSearchCV(estimator=neigh,param_grid=parameters,scoring=f1_scorer)